Statements (34)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
speech representation model
|
| gptkbp:author |
gptkb:Xiaodong_Liu
gptkb:Jianfeng_Gao Chengyi Wang Jian Wu Michael Zeng Shujie Liu Xuedong Huang Yao Qian Yu Wu |
| gptkbp:availableOn |
gptkb:GitHub
|
| gptkbp:basedOn |
transformer architecture
|
| gptkbp:citation |
1000+
|
| gptkbp:developedBy |
gptkb:Microsoft_Research
|
| https://www.w3.org/2000/01/rdf-schema#label |
WavLM
|
| gptkbp:input |
raw audio waveform
|
| gptkbp:language |
English
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:notablePublication |
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
|
| gptkbp:openSource |
true
|
| gptkbp:output |
speech representations
|
| gptkbp:publishedIn |
gptkb:NeurIPS_2022
|
| gptkbp:relatedTo |
gptkb:Wav2Vec_2.0
gptkb:HuBERT |
| gptkbp:releaseYear |
2021
|
| gptkbp:trainer |
Libri-Light dataset
VoxPopuli dataset |
| gptkbp:usedFor |
speech recognition
emotion recognition speaker diarization speech enhancement speaker verification |
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|